Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    assignment and versioning syntax in structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or version assignment

    np_acts-logits-general · gemini-2.0-flash

    assignments and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ritro
    -0.30
     aihe
    -0.30
    ไข
    -0.30
     who
    -0.29
     suun
    -0.29
     realizzato
    -0.29
     still
    -0.28
     hän
    -0.28
     handen
    -0.28
     íntimo
    -0.28
    POSITIVE LOGITS
     AssemblyVersion
    0.68
    ंदीखरीदारी
    0.67
     виправивши
    0.66
    windowFixed
    0.61
    IsMutable
    0.61
    LookAnd
    0.60
     Version
    0.60
    posedge
    0.60
    twimg
    0.60
    лтамалар
    0.60
    Act Density 0.070%

    No Known Activations